© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4769
    Prev
    Next
    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerToggle
    -0.57
    Билгалдахарш
    -0.57
    MethodManager
    -0.54
    +#+#
    -0.53
     Profiles
    -0.52
    PropertyChanging
    -0.52
     kasarigan
    -0.52
    ViewFeatures
    -0.51
    fromCharCode
    -0.50
    KURZBESCHREIBUNG
    -0.50
    POSITIVE LOGITS
    OrWhiteSpace
    0.50
     publications
    0.49
     <<<<<<<<<<<<<<
    0.46
     letzten
    0.46
    twimg
    0.44
    Numerous
    0.43
    registrer
    0.43
    RTLI
    0.43
    &=&
    0.43
     roce
    0.43
    Activations Density 0.000%

    No Known Activations